Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 19787
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and natural phenomena, particularly related to environmental impact or physical events

    oai_token-act-pair · gpt-3.5-turbo

    references to maritime and aviation-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oken
    -0.73
    女
    -0.68
    iquette
    -0.67
    calling
    -0.67
    atform
    -0.66
    nces
    -0.65
    ACP
    -0.64
    Freedom
    -0.63
    venge
    -0.62
    èĢħ
    -0.61
    POSITIVE LOGITS
     astronomers
    0.86
     theoret
    0.77
     microsc
    0.75
     scientists
    0.74
     Scientific
    0.74
     IPM
    0.71
     theorists
    0.70
     Scientists
    0.68
     archaeologists
    0.68
    eval
    0.64
    Activations Density 1.361%

    No Known Activations